检索结果-内蒙古大学图书馆

A novel method for clustering cellular data to improve classification

Neural Regeneration Research 2025年第9期20卷 2697-2705页

作者： Diek W.Wheeler Giorgio A.Ascoli Center for Neural Informatics Structures&PlasticityKrasnow Institute for Advanced Study Bioengineering Department Volgenau School of Engineering George Mason University FairfaxVAUSA

Many fields,such as neuroscience,are experiencing the vast prolife ration of cellular data,underscoring the need fo r organizing and interpreting large datasets.A popular approach partitions data into manageable subsets via hierarchical clustering,but objective methods to determine the appropriate classification granularity are *** recently introduced a technique to systematically identify when to stop subdividing clusters based on the fundamental principle that cells must differ more between than within *** we present the corresponding protocol to classify cellular datasets by combining datadriven unsupervised hierarchical clustering with statistical *** general-purpose functions are applicable to any cellular dataset that can be organized as two-dimensional matrices of numerical values,including molecula r,physiological,and anatomical *** demonstrate the protocol using cellular data from the Janelia MouseLight project to chara cterize morphological aspects of neurons.

关键词： cellular data clustering dendrogram data classification Levene's one-tailed statistical test unsupervised hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

Identification of markers predicting clinical course in patients with Behcet disease by combination of machine learning and unbiased clustering analysis

引用

GRAEFES ARCHIVE FOR CLINICAL AND EXPERIMENTAL OPHTHALMOLOGY 2025年 1-10页

作者： Tsubota, Kinya Usui, Yoshihiko Shimizu, Hiroyuki Goto, Hiroshi Tokyo Med Univ Dept Ophthalmol 6-7-1 NishishinjukuShinjuku Ku Tokyo 1600023 Japan

Purpose Behcet's disease (BD) is a multisystem inflammatory disorder with diverse clinical manifestations. Identifying biomarkers predictive of clinical outcomes, such as tumor necrosis factor (TNF) inhibitor initiation and ocular inflammatory attack frequency, is critical for improving management. This study aimed to identify biomarkers predicting the clinical course of BD using peripheral blood test data and unbiased clustering combined with machine learning. Methods A retrospective cohort study of 238 BD patients diagnosed at Tokyo Medical University Hospital (2004-2020) was conducted. unsupervised hierarchical clustering was applied to peripheral blood data, dividing patients into distinct groups. Machine learning techniques were used to explore biomarkers predicting the clinical course. Results Cluster analysis identified four groups: Group A (low C-reactive protein), Group B (high angiotensin-converting enzyme), Group C (high anti-streptolysin O), and Group D (low neutrophil count). Group C had a higher rate of TNF inhibitor initiation (47%, p = 0.04), while Group D had fewer ocular inflammation attacks per year (1.4, p = 0.04). Logistic regression analysis identified red blood cell count (p < 0.01) and monocyte percentage (p = 0.02) as predictive biomarkers for TNF inhibitor initiation. Machine learning further confirmed mean corpuscular hemoglobin concentration (MCHC) as a significant predictor of TNF inhibitor initiation. Additionally, multiple regression analysis identified the neutrophil/lymphocyte ratio as a predictor of the number of inflammatory attacks per year (p = 0.02). Conclusions unsupervised clustering of blood test data identified distinct BD clinical phenotypes. Monocyte percentage may predict TNF inhibitor initiation, while neutrophil/lymphocyte ratio may predict ocular inflammation frequency, highlighting pathophysiologic heterogeneity in BD.

关键词： Behcet's disease Machine learning TNF inhibitor unsupervised hierarchical clustering Monocyte percentage Neutrophil/lymphocyte ratio

来源：评论

学校读者我要写书评

暂无评论

DNA methylation profiling of meningiomas highlights clinically distinct molecular subgroups

引用

JOURNAL OF NEURO-ONCOLOGY 2023年第2期161卷 339-356页

作者： Singh, Jyotsna Sharma, Ravi Shukla, Nidhi Narwal, Priya Katiyar, Amit Mahajan, Swati Sahu, Saumya Garg, Ajay Sharma, Mehar C. C. Suri, Ashish Sarkar, Chitra Suri, Vaishali All India Inst Med Sci Neurosci Ctr Neuropathol Lab New Delhi India All India Inst Med Sci Dept Neurosurg New Delhi India All India Inst Med Sci CCRF New Delhi India All India Inst Med Sci Dept Neuroradiol New Delhi India All India Inst Med Sci Dept Pathol New Delhi India

Background Introduction of the classification of brain tumours based on DNA methylation profile has significantly changed the diagnostic approach. Due to the paucity of data on the molecular profiling of meningiomas and their clinical implications, no effective therapies and new treatments have been implemented. Methods DNA methylation profiling, copy number analysis, targeted sequencing and H3K27me3 expression was performed on 35 meningiomas and 5 *** unsupervised hierarchical clustering (UHC) analysis revealed four distinct molecular subgroups: Malignant;Intermediate;Benign A, and Benign B. Molecular heterogeneity was observed within the same grade as the Intermediate, Benign A, and Benign B subgroups were composed of WHO grade 1 as well as grade 2 cases. There was association of mutations with distinct methylation subgroups (NF2, AKT1, SMO, TRAF7 and pTERT). Loss of chromosome 22q was observed across all subgroups. 1p/14q co-deletion was seen in 50% of malignant and intermediate while CDKN2A loss was predominantly observed in malignant subgroup (50%). Majority of malignant (75%) and a small proportion of other subgroups (Intermediate: 25%, Benign A: 38.5%, and Benign B: 20%) harboured H3K27me3 loss. 38,734 genes were dysregulated amongst the four subgroups. DKFZ classified 71% cases with acceptable score. On survival analysis, methylation profiling had significant impact on progression-free-survival in WHO grade1 and 2 meningiomas (p = 0.0051).Conclusion Genome-wide DNA methylation profiling highlights clinically distinct molecular subgroups and heterogeneity within the same grade of meningiomas. Molecular profiling can usher in a paradigm shift in meningioma classification, prognostic prediction, and treatment strategy.

关键词： Methylation profiling Targeted sequencing unsupervised hierarchical clustering Methylation subgroups DKFZ classifier

来源：评论

学校读者我要写书评

暂无评论

Explaining Massive-Training Artificial Neural Networks in Medical Image Analysis Task Through Visualizing Functions Within the Models 26th

Explaining Massive-Training Artificial Neural Networks in Me...

引用

26th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)

作者： Jin, Ze Pang, Maolin Yang, Yuqiao Mahdi, Fahad Parvez Qu, Tianyi Sasage, Ren Suzuki, Kenji Tokyo Inst Technol Inst Innovat Res Biomed Artificial Intelligence Res Unit Meguro Kanagawa Japan

ISBN: (纸本)9783031438943;9783031438950

In this study, we proposed a novel explainable artificial intelligence (XAI) technique to explainmassive-training artificial neural networks (MTANNs). Firstly, we optimized the structure of anMTANNto find a compact model that performs equivalently well to the original one. This enables to "condense" functions in a smaller number of hidden units in the network by removing "redundant" units. Then, we applied an unsupervised hierarchical clustering algorithm to the function maps in the hidden layers with the single-linkage method. From the clustering and visualization results, we were able to group the hidden units into those with similar functions together and reveal the behaviors and functions of the trained MTANN models. We applied this XAI technique to explain the MTANN model trained to segment liver tumors in CT. The original MTANN model with 80 hidden units (F1 = 0.6894, Dice = 0.7142) was optimized to the one with nine hidden units (F1 = 0.6918, Dice = 0.7005) with almost equivalent performance. The nine hidden units were clustered into three groups, and we found the following three functions: 1) enhancing liver area, 2) suppressing non-tumor area, and 3) suppressing the liver boundary and false enhancement. The results shed light on the "black-box" problem with deep learning (DL) models;and we demonstrated that our proposed XAI technique was able to make MTANN models "transparent".

关键词： Deep Learning Explainable AI (XAI) Visualizing Functions Liver Tumor Segmentation unsupervised hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

A MUCINs expression signature impacts overall survival in patients with clear cell renal cell carcinoma

引用

CANCER MEDICINE 2021年第17期10卷 5823-5838页

作者： Meng, Hui Jiang, Xuewen Huang, Huangwei Shen, Neng Guo, Changsheng Yu, Chunxiao Yin, Gang Wang, Yu Qilu Hosp Dept Urol Jinan Shandong Peoples R China Shandong Univ Cheeloo Coll Med Jinan Shandong Peoples R China Taian TSCM Hosp Dept Surg Tai An Shandong Peoples R China Liaoning Hosp Tradit Chinese Med Dept Urol Shandong Peoples R China Cent Hosp Zaozhuang Min Grp Dept Urol Shandong Peoples R China Qilu Hosp Dept Obstet & Gynecol Ctr Reprod Med Jinan Shandong Peoples R China

Background Kidney cancer, especially clear cell renal cell carcinoma (ccRCC), is one of the most common cancers in the urinary system. Previous studies suggested that certain members of MUCINs could serve as independent predictors for the survival of ccRCC patients. None of them, however, is robust enough to predict prognosis accurately. Objective To analyze the correlation of MUCINs alterations and their expression levels with the prognosis of ccRCC patients and develop a prognosis-related predictor. Methods We applied whole-exome sequencing in samples from 22 Chinese ccRCC patients to identify genetic alterations in MUCIN genes and analyzed their genetic alterations, expression, and correlation with survival using the TCGA, , and datasets. Result Genetic alternations in MUCINs were identified in 91% and 51% of ccRCC patients in our cohort and the TCGA database, respectively. No correlation with survival was found for the genetic alterations. Using unsupervised clustering analysis of gene expression, we identified two major clusters of MUCIN expression patterns. Cluster 1 was characterized by a global overexpression of MUC1, MUC12, MUC13, MUC16, and OVGP1;and cluster 2 was characterized by a global overexpression of MUC4, MUC5B, MUC6, MUC20, EMCN, and MCAM. Patients with cluster 1 expression pattern had significantly shorter overall survival time and worse clinical features, including higher tumor grades and metastasis. Meanwhile, they had a higher level of mutation counts and more infiltrated immune cells, but lower enrichment in angiogenesis signature genes. A five-MUCINs expression signature was constructed from cluster 1, and notably, it was demonstrated to be associated with shorter overall survival. A similar worse clinical feature, lower angiogenesis but the more immune signature, was identified in samples presented with signature 1. In the validation data set , patients with signature 1 were also associated with a trend of poor survival outcomes. Conclusion

关键词： ccRCC MUCIN overall survival prognosis unsupervised hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

CD8+T-cell marker genes reveal different immune subtypes of oral lichen planus by integrating single-cell RNA-seq and bulk RNA-sequencing

引用

BMC ORAL HEALTH 2023年第1期23卷 464-464页

作者： Zhang, Jinhao Peng, Gaoge Chi, Hao Yang, Jinyan Xie, Xixi Song, Guobin Tran, Lisa Jia Xia, Zhijia Tian, Gang Southwest Med Univ Sch Stomatol Luzhou Peoples R China Southwest Med Univ Clin Med Coll Luzhou Peoples R China Ludwig Maximilians Univ Munchen Dept Gen Visceral & Transplant Surg Munich Germany Affiliated Hosp Southwest Med Univ Dept Lab Med Luzhou Peoples R China

BackgroundOral lichen planus (OLP) is a local autoimmune disease induced by T-cell dysfunction that frequently affects middle-aged or elderly people, with a higher prevalence in women. CD8 + T cells, also known as killer T cells, play an important role in the progression and persistence of OLP. In order to identify different OLP subtypes associated with CD8 + T cell pathogenesis, consensus clustering was *** this study, we preprocessed and downscaled the OLP single-cell dataset GSE211630 cohort downloaded from Gene Expression Omnibus (GEO) to finally obtain the marker genes of CD8 + T cells. Based on the expression of marker genes, we classified OLP patients into CMGs subtypes using unsupervised clustering analysis. The gene expression profiles were analyzed by WGCNA using the "WGCNA" R package based on the clinical disease traits and typing results, and 108 CD8 + T-cell related OLP pathogenicity-related genes were obtained from the intersection. Patients were once again classified into gene subtypes based on intersection gene expression using unsupervised clustering *** obtaining the intersecting genes of CD8 + T cells related to pathogenesis, OLP patients can be precisely classified into two different subtypes based on unsupervised clustering analysis, and subtype B has better immune infiltration results, providing clinicians with a reference for personalized *** of OLP into different subtypes improve our current understanding of the underlying pathogenesis of OLP and provides new insights for future studies.

关键词： Autoimmunity OLP CD8+T cells unsupervised hierarchical clustering Single-cell sequencing

来源：评论

学校读者我要写书评

暂无评论

Prostate cancer identification via photoacoustic spectroscopy and machine learning

引用

PHOTOACOUSTICS 2021年 23卷 100280-100280页

作者： Chen, Yingna Xu, Chengdang Zhang, Zhaoyu Zhu, Anqi Xu, Xixi Pan, Jing Liu, Ying Wu, Denglong Huang, Shengsong Cheng, Qian Tongji Univ Sch Phys Sci & Engn Inst Acoust Shanghai Peoples R China Tongji Univ Tongji Hosp Dept Urol Sch Med Shanghai Peoples R China Tongji Univ Sch Software Engn Shanghai Peoples R China Tongji Univ Shanghai Res Inst Intelligent Autonomous Syst Shanghai Peoples R China

Photoacoustic spectroscopy can generate abundant chemical and physical information about biological tissues. However, this abundance of information makes it difficult to compare these tissues directly. Data mining methods can circumvent this problem. We describe the application of machine-learning methods (including unsupervised hierarchical clustering and supervised classification) to the diagnosis of prostate cancer by photoacoustic spectrum analysis. We focus on the content and distribution of hemoglobin, collagen, and lipids, because these molecules change during the development of prostate cancer. A higher correlation among the ultrasonic power spectra of these chemical components is observed in cancerous than in normal tissues, indicating that the microstructural distributions in cancerous tissues are more consistent. Different classifiers applied in cancer-tissue diagnoses achieved an accuracy of 82 % (better than that of standard clinical methods). The technique thus exhibits great potential for painless early diagnosis of aggressive prostate cancer.

关键词： Photoacoustic physio-chemical analysis Prostate cancer Machine learning unsupervised hierarchical clustering Supervised classification

来源：评论

学校读者我要写书评

暂无评论

Comprehensive analysis of the prognostic value of the chemokine-like factor-like MARVEL transmembrane domain-containing family in gastric cancer

Comprehensive analysis of the prognostic value of the chemok...

引用

2022第27届广东省药师周大会

作者： Zhikun Liang Jingwen Xie Lihong Huang Yaoyao Huang Yuwen Zhang Ruanxin Ma Zhuoling Zheng Qinbo Wang Xiaoyan Li Department of Pharmacy the Sixth Affiliated HospitalSun Yat-Sen University

Background:Thechemokine-like factor(CKLF)-like MARVEL transmembrane domain-containing(CMTM) family refers to a family of transcriptional repressor *** areclosely associated withthe epigenetic regulatory mechanisms and development of multiple malignancies,includinggastric ***,theirspecific biological functions and prognostic valuesin gastric cancerhave yet to be ***:Tumor sample datasets were retrieved and analyzed using databases including Oncomine,STRING,GEPIA2,cBioportal,and Kaplan-Meier *** investigate the prognostic role of CMTMs in gastric cancer,we applied unsupervised hierarchical clustering analysis of CMTM gene expression ***:While the m RNA levels of CMTM1/3/6/7/8 were upregulated in gastric cancer,CMTM2/4/5 showed no statistically significant difference at the mRNA level in patients with gastric ***,the mRNA expressions of different CMTMs exhibited strong correlations with various clinical parameters of patients with gastric cancer,including tumor stage,metastatic lymph node status,*** status,and tumor ***,the results suggested that elevated levels of CMTM3/5 mRNA had a significant association(P<0.05) with poor overall survival,progression-free survival,and post-progression ***,elevated expression of CMTM2/4/6 mRNA had a significantassociation with better overall survival,progression-free survival,and post-progression *** hierarchical clustering analysis successfully identified2 major clusters of patients as follows:signature #1:CMTM4/6/8 and signature #2:CMTM1/2/3/5/*** #2 was closely correlated with poorer overall survival,which indicatedthat the expression pattern of the CMTM family could be a novel prognostic factor for patients with gastric ***:These results suggest that the expression levels of CMTM genes possibly have prognostic value as a biomarker of gastric cancer.

关键词： Gastric cancer CMTM family genes prognosis biomarkers unsupervised hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

An automated data extraction and classification pipeline to identify a novel type of neuron within the dorsal striatum based on single-cell patch clamp and confocal imaging data

引用

DATA IN BRIEF 2020年 32卷 106148页

作者： Mao, Miaomiao Nair, Aditya Augustine, George J. Nanyang Technol Univ Lee Kong Chian Sch Med Singapore Singapore Inst Mol & Cell Biol Singapore Singapore Agcy Sci & Technol Singapore Bioimaging Consortium Singapore Singapore

We employed electrophysiological and fluorescence imaging techniques to describe the characteristics of a novel type of neuron discovered in the mouse dorsal striatum. Transgenic mice that express YFP-tagged channelrhodopsin-2 (ChR2) in neurons driven by the promoter for tyrosine hydroxylase (TH) were used and the intrinsic electrical properties of YFPpositive neurons in the dorsal striatum of these mice were characterized using whole -cell patch clamping in acute brain slices. Passive membrane properties - such as membrane capacitance, resting membrane potential and input resistance -and action potential properties- such as amplitude, kinetics and adaptation - were extracted from raw data files. Filling these neurons with neurobiotin enabled visualization of neuronal morphology via immunohistochemical labeling with streptavidin-conjugated fluorophore. Subsequent twophoton imaging allowed analyses of morphological properties such as somaticsize, dendritic branching (Sholl analysis) and density of dendritic spines. Unbiased analyses and hierarchical clustering of both morphological and functional data allowed us to identify a previously undescribed type of striatal neuron with unique properties. To facilitate identification of this new cell type, an end-to-end automated electrophysiology pipeline was developed that extracts relevant parameters and determines striatal neuron identity using neural-network based classifiers. These data and the software tool will permit other investigators to identify this novel type of neuron in their studiesand thereby better understand theroles thatthese neuronsplay in dorsal striatum circuitry. (C) 2020 The Authors. Published by Elsevier Inc.

关键词： Neuron classification Whole-cell patch clamping Two-photon imaging Intrinsic electrical properties unsupervised hierarchical clustering Machine-learning aided classification

来源：评论

学校读者我要写书评

暂无评论

Regional Differences in mRNA and lncRNA Expression Profiles in Non-Failing Human Atria and Ventricles

引用

SCIENTIFIC REPORTS 2018年第1期8卷 1-1页

作者： Johnson, Eric K. Matkovich, Scot J. Nerbonne, Jeanne M. Washington Univ Sch Med Dept Med Cardiovasc Div St Louis MO 63110 USA Washington Univ Sch Med Dept Dev Biol St Louis MO 63110 USA

The four chambers of the human heart play distinct roles in the maintenance of normal cardiac function, and are differentially affected by inherited/acquired cardiovascular disease. To probe the molecular determinants of these functional differences, we examined mRNA and lncRNA expression profiles in the left (LA) and right (RA) atria, the left (LV) and right (RV) ventricles, and the interventricular septum (IVS) of non-failing human hearts (N = 8). Analysis of paired atrial and ventricular samples (n = 40) identified 5,747 mRNAs and 2,794 lncRNAs that were differentially (>1.5 fold;FDR < 0.05) expressed. The largest differences were observed in comparisons between the atrial (RA/LA) and ventricular (RV/LV/IVS) samples. In every case (e.g., LA vs LV, LA vs RV, etc.), >2,300 mRNAs and >1,200 lncRNAs, corresponding to 17-28% of the total transcripts, were differentially expressed. Heterogeneities in mRNA/lncRNA expression profiles in the LA and RA, as well as in the LV, RV and IVS, were also revealed, although the numbers of differentially expressed transcripts were substantially smaller. Gender differences in mRNA and lncRNA expression profiles were also evident in non-failing human atria and ventricles. Gene ontology classification of differentially expressed gene sets revealed chamber-specific enrichment of numerous signaling pathways.

关键词： lncRNA Expression Profiles Paired Tissue Samples Myocardial Infarction Associated Transcript (MIAT) unsupervised hierarchical clustering Differential Expression Analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：